kubewhy
Air-gapped Kubernetes root-cause analysis. Everything tells you what is broken; kubewhy tells you why — a local LLM reads real logs, events and resource limits to find the cause. Read-only, verifies its own claims, nothing leaves your network.
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
ravisinghrajput95
Source: github_repo_search
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
TRIAGE_API_TOKENBearer token for machine callers; unset means no authHOSTNAMETRIAGE_MODELModel name the provider servesTRIAGE_THINKTRIAGE_INVESTIGATION_BUDGETTRIAGE_AUDITOne audit record per investigation. 0 turns it offTRIAGE_AUDIT_LOGAppend audit records to this file as well as to the log streamTRIAGE_BACKENDOLLAMA_TIMEOUTSeconds before a model call is abandonedTRIAGE_OPENAI_BASE_URLOPENAI_API_KEYCredential for an OpenAI-protocol providerOLLAMA_KEEP_ALIVEHow long Ollama holds the weights after a request, e.g. 24h. Forwarded on every call, because the client library does not read it. Unset means the server's own default (5m)TRIAGE_STUCK_AFTERSeconds a pod may sit in ContainerCreating or PodInitializing before the controller treats it as a fault rather than a start-upTRIAGE_LEASE_TTLTRIAGE_NAMESPACESTRIAGE_COOLDOWNTRIAGE_MAX_PER_HOURTRIAGE_SKIP_EXISTINGTRIAGE_STATE_DBWith set the result survives a restart of this process.TRIAGE_AUTH_MODEproxy, so it refuses a request carrying no identity header —TRIAGE_PRIMARY_RETRY_SECONDSHow long a failed primary is skipped before being tried againLOG_FORMATtext for human-readable logsLOG_LEVELStandard Python levelsTRIAGE_POD_CACHETRIAGE_POD_CACHE_MAX_AGETRIAGE_SINKSLACK_WEBHOOK_URLIncoming webhook, bound to one channelSLACK_BOT_TOKENBot token (xoxb-…). With SLACK_CHANNEL, posts via chat.postMessage and wins over a webhookSLACK_CHANNELBot token (xoxb-…). With SLACK_CHANNEL, posts via chat.postMessage and wins over a webhookSLACK_APP_TOKENApp-level token (xapp-…) for the Socket Mode bot in slack_socket.py. Needs connections:writeTRIAGE_JOB_TTLSeconds an /ask job result is kept before purgingOLLAMA_HOSTBase URL. Falls back to OLLAMA_HOST for the ollama providerK8S_TIMEOUTmulti-megabyte response inside . Narrow with namespaces= — aTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
1/1 tools missing one or more hints — _tool (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint). OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/ravisinghrajput95/kubewhy)?variant=verified to the badge URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check